Advertisement

Single Image Deblurring Using Motion Density Functions

  • Ankit Gupta
  • Neel Joshi
  • C. Lawrence Zitnick
  • Michael Cohen
  • Brian Curless
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6311)

Abstract

We present a novel single image deblurring method to estimate spatially non-uniform blur that results from camera shake. We use existing spatially invariant deconvolution methods in a local and robust way to compute initial estimates of the latent image. The camera motion is represented as a Motion Density Function (MDF) which records the fraction of time spent in each discretized portion of the space of all possible camera poses. Spatially varying blur kernels are derived directly from the MDF. We show that 6D camera motion is well approximated by 3 degrees of motion (in-plane translation and rotation) and analyze the scope of this approximation. We present results on both synthetic and captured data. Our system out-performs current approaches which make the assumption of spatially invariant blur.

Keywords

Camera Motion Latent Image Blind Deconvolution Ground Truth Image Blur Kernel 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Richardson, W.H.: Bayesian-based iterative method of image restoration. Journal of the Optical Society of America (1917-1983) (1972)Google Scholar
  2. 2.
    Shan, Q., Jia, J., Agarwala, A.: High-quality motion deblurring from a single image. In: ACM SIGGRAPH 2008 Papers (2008)Google Scholar
  3. 3.
    Likas, A.C., Galatsanos, N.P.: A variational approach for bayesian blind image deconvolution (2004)Google Scholar
  4. 4.
    Fergus, R., Singh, B., Hertzmann, A., Roweis, S.T., Freeman, W.T.: Removing camera shake from a single photograph. In: ACM SIGGRAPH 2006 Papers (2006)Google Scholar
  5. 5.
    Yuan, L., Sun, J., Quan, L., Shum, H.Y.: Image deblurring with blurred/noisy image pairs. In: ACM SIGGRAPH 2007 Papers (2007)Google Scholar
  6. 6.
    Joshi, N., Zitnick, L., Szeliski, R., Kriegman, D.: Image deblurring and denoising using color priors. In: Proceedings of IEEE CVPR ’09 (2009)Google Scholar
  7. 7.
    Ben-Ezra, M., Nayar, S.K.: Motion-based motion deblurring. IEEE Trans. Pattern Analysis Machine Intelligence (2004)Google Scholar
  8. 8.
    Levin, A., Sand, P., Cho, T.S., Durand, F., Freeman, W.T.: Motion-invariant photography. In: ACM SIGGRAPH 2008 Papers (2008)Google Scholar
  9. 9.
    Agarwal, A., Xu, Y.: Coded exposure deblurring: Optimized codes for psf estimation and invertibility. In: Proceedings of IEEE CVPR ’09 (2009)Google Scholar
  10. 10.
    Agarwal, A., Xu, Y., Raskar, R.: Invertible motion blur in video. In: ACM SIGGRAPH 2009 Papers (2009)Google Scholar
  11. 11.
    Raskar, R., Agrawal, A., Tumblin, J.: Coded exposure photography: motion deblurring using fluttered shutter. In: ACM SIGGRAPH 2006 Papers (2006)Google Scholar
  12. 12.
    Levin, A.: Blind motion deblurring using image statistics. In: Advances in Neural Information Processing Systems (2007)Google Scholar
  13. 13.
    Jia, J.: Single image motion deblurring using transparency. In: Proceedings of IEEE CVPR ’07, pp. 1–8 (2007)Google Scholar
  14. 14.
    Joshi, N., Szeliski, R., Kriegman, D.J.: Psf estimation using sharp edge prediction. In: Proceedings of IEEE CVPR ’08 (2008)Google Scholar
  15. 15.
    Levin, A., Weiss, Y., Durand, F.: Understanding and evaluating blind deconvolution algorithms. In: Proceedings of IEEE CVPR ’09 (2009)Google Scholar
  16. 16.
    Tai, Y.W., Du, H., Brown, M., Lin, S.: Image/video deblurring using a hybrid camera. In: Proceedings of IEEE CVPR ’08 (2008)Google Scholar
  17. 17.
    Tai, Y.W., Kong, N., Lin, S., Shin, S.Y.: Coded exposure imaging for projective motion deblurring. In: Proceedings of IEEE CVPR ’10 (2010)Google Scholar
  18. 18.
    Dai, S., Wu, Y.: Motion from blur. In: Proceedings of IEEE CVPR ’08 (2008)Google Scholar
  19. 19.
    Shan, Q., Xiong, W., Jia, J.: Rotational motion deblurring of a rigid object from a single image. In: Proceedings of IEEE ICCV ’07 (2007)Google Scholar
  20. 20.
    Hirsch, M., Sra, S., Schölkopf, B., Harmeling, S.: Efficient filter flow for space-variant multiframe blind deconvolution. In: Proceedings of IEEE CVPR ’10 (2010)Google Scholar
  21. 21.
    Whyte, O., Sivic, J., Zisserman, A., Ponce, J.: Non-uniform deblurring for shaken images. In: Proceedings of IEEE CVPR ’10 (2010)Google Scholar
  22. 22.
    Seitz, S., Winder, S.: Filter flow. In: Proceedings of IEEE ICCV ’09 (2009)Google Scholar
  23. 23.
    Weiss, Y., Freeman, W.T.: What makes a good model of natural images? In: Proceedings of IEEE CVPR ’07 (2007)Google Scholar
  24. 24.
    Joshi, N., Kang, S.B., Zitnick, C.L., Szeliski, R.: Image deblurring using inertial measurement sensors. In: ACM SIGGRAPH 2007 Papers (2010)Google Scholar
  25. 25.
    Gupta, A.: Project webpage: Single image deblurring using motion density functions (2010), http://www.grail.cs.washington.edu/projects/mdf_deblurring
  26. 26.
    Reinhard, E., Shirley, P., Ashikhmin, M., Troscianko, T.: Second order image statistics in computer graphics. In: Proceedings of the ACM Symposium on Applied Perception in Graphics and Visualization (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Ankit Gupta
    • 1
  • Neel Joshi
    • 2
  • C. Lawrence Zitnick
    • 2
  • Michael Cohen
    • 2
  • Brian Curless
    • 1
  1. 1.University of Washington 
  2. 2.Microsoft Research 

Personalised recommendations